Catalog
Every model the sweep touched, in one table. The readings on Insights each answer one question; this answers the ones not thought of yet — sort on any dimension, filter to the population worth comparing.
The dimensions are collected by different means and do not cover the same population: a model can draw heavy traffic and carry no published benchmark, or score well and route almost nothing. A blank cell means not measured, never zero — and sorting sinks a blank to the bottom whichever way the column points, so an untested model never floats to the top as the cheapest thing here.
| Model | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| openai/gpt-5.6-luna | 2.6T | 14.18% | 1.44× | $0.100 | 37.5 | 71.4 | 42.7 | $0.003 | 54 |
| deepseek/deepseek-v4-flash-0731 | 1.7T | 9.59% | 0.90× | $0.040 | 34.5 | 69.1 | 41.7 | $0.001 | 18 |
| tencent/hy4-preview | 1.7T | 9.52% | 1.25× | — | — | — | — | — | — |
| z-ai/glm-5.3-flash | 1.6T | 8.70% | 1.30× | $0.075 | 41.9 | 71.5 | 51.2 | $0.002 | 18 |
| deepseek/deepseek-v4.1-flash | 1.3T | 7.08% | 5.43× | $0.150 | 39.5 | 0.0 | 0.0 | $0.004 | 24 |
| xiaomi/mimo-v2.5 | 1.2T | 6.38% | 0.98× | $0.119 | 22.3 | 56.8 | 17.4 | $0.005 | 2 |
| tencent/hy3 | 775.7B | 4.28% | 0.83× | — | — | — | — | — | — |
| deepseek/deepseek-v4-flash | 647.7B | 3.57% | 0.79× | $0.050 | 24.8 | 52.0 | 27.9 | $0.002 | 18 |
| nvidia/nemotron-3-ultra-550b-a55b | 460.0B | 2.54% | 0.66× | $0.500 | 23.4 | 49.3 | 21.7 | $0.021 | 21 |
| openai/gpt-5.6-sol | 310.5B | 1.71% | 1.18× | $1.00 | 47.1 | 77.4 | 50.5 | $0.021 | 39 |
| google/gemini-3.8-flash | 299.5B | 1.65% | 2.01× | $0.375 | 41.2 | 76.3 | 41.1 | $0.009 | 114 |
| z-ai/glm-5.3 | 295.0B | 1.63% | 1.01× | $0.877 | 44.9 | 74.8 | 53.4 | $0.019 | 22 |
| meta/muse-spark-1.3-contributor | 272.5B | 1.50% | 2.32× | — | — | — | — | — | — |
| anthropic/claude-sonnet-5 | 244.0B | 1.35% | 1.20× | $2.00 | 38.4 | 71.5 | 44.3 | $0.052 | 47 |
| z-ai/glm-5.2 | 239.1B | 1.32% | 0.55× | $0.487 | 34.0 | 68.8 | 39.4 | $0.014 | 25 |
| upstage/solar-pro4 | 231.7B | 1.28% | 1.37× | — | — | — | — | — | — |
| minimax/minimax-m3 | 209.8B | 1.16% | 0.38× | $0.230 | 29.6 | 58.6 | 30.8 | $0.008 | 70 |
| deepseek/deepseek-v4-pro | 208.4B | 1.15% | 0.82× | $0.955 | 30.9 | 59.4 | 27.7 | $0.031 | 36 |
| moonshotai/kimi-k3 | 204.0B | 1.13% | 0.80× | $2.10 | 43.8 | 76.2 | 50.6 | $0.048 | 39 |
| poolside/laguna-s-2.1 | 172.4B | 0.95% | 0.75× | — | — | — | — | — | — |
| anthropic/claude-opus-5 | 168.2B | 0.93% | 0.64× | $5.00 | 50.7 | 78.0 | 56.2 | $0.099 | 68 |
| inclusionai/ling-3.0-flash-fin | 161.0B | 0.89% | 2.00× | — | — | — | — | — | — |
| deepseek/deepseek-v4-pro-0813 | 148.9B | 0.82% | 0.88× | $0.660 | 36.3 | 68.8 | 42.3 | $0.018 | 45 |
| google/gemini-3-flash-preview | 119.2B | 0.66% | 0.89× | — | — | — | — | — | — |
| google/gemini-2.5-flash-lite | 105.1B | 0.58% | 0.83× | — | — | — | — | — | — |
| dots-studio/dots-3-note-preview | 102.6B | 0.57% | 2.31× | — | — | — | — | — | — |
| openai/gpt-6-astra | 101.3B | 0.56% | 2.77× | $5.00 | 52.8 | 76.9 | 51.5 | $0.095 | 20 |
| google/gemini-3.7-flash | 93.6B | 0.52% | 0.28× | $0.375 | 39.4 | 76.1 | 36.4 | $0.009 | 117 |
| openai/gpt-5.6-terra | 91.3B | 0.50% | 0.93× | $1.00 | 42.3 | 76.7 | 43.7 | $0.024 | 54 |
| inclusionai/ling-3.0-flash-vl | 84.1B | 0.46% | 8.23× | $0.060 | 24.8 | 57.0 | 30.0 | $0.002 | 14 |
| openai/gpt-oss-120b | 83.9B | 0.46% | 1.04× | $0.030 | 12.3 | 30.4 | 6.2 | $0.002 | 45 |
| google/gemini-3.1-flash-lite | 76.7B | 0.42% | 1.05× | — | — | — | — | — | — |
| nvidia/nemotron-3.5-lightning | 75.1B | 0.41% | 0.48× | $0.065 | 13.6 | 26.8 | 6.1 | $0.005 | 55 |
| google/gemini-2.5-flash | 74.6B | 0.41% | 1.00× | — | — | — | — | — | — |
| qwen/qwen3.8-flash | 74.5B | 0.41% | 3.13× | — | — | — | — | — | — |
| anthropic/claude-fable-5.1 | 72.6B | 0.40% | 2.53× | $10.00 | 53.4 | 81.6 | 58.0 | $0.187 | 37 |
| anthropic/claude-sonnet-4.6 | 71.6B | 0.40% | 0.54× | $3.00 | 30.5 | 63.0 | 33.1 | $0.098 | 39 |
| deepseek/deepseek-v3.2 | 58.4B | 0.32% | 0.82× | — | — | — | — | — | — |
| x-ai/grok-4.6 | 56.7B | 0.31% | 0.82× | $2.00 | 44.4 | 76.8 | 53.4 | $0.045 | 45 |
| thinkingmachines/inkling | 56.2B | 0.31% | 1.49× | $0.950 | 25.5 | 52.1 | 24.3 | $0.037 | 160 |
| anthropic/claude-opus-4.8 | 55.6B | 0.31% | 0.82× | $5.00 | 42.0 | 74.3 | 42.6 | $0.119 | 55 |
| google/gemma-4-31b-it | 54.5B | 0.30% | 0.94× | $0.090 | 15.4 | 43.4 | 6.7 | $0.006 | 37 |
| qwen/qwen3.7-flash | 53.6B | 0.30% | 1.58× | — | — | — | — | — | — |
| nex-agi/nex-n2.5-pro | 52.5B | 0.29% | 3.43× | — | — | — | — | — | — |
| nvidia/nemotron-3-super-120b-a12b | 51.7B | 0.29% | 0.80× | $0.080 | 13.6 | 37.7 | 4.1 | $0.006 | 12 |
| qwen/qwen3.8-max-0902 | 47.0B | 0.26% | 2.25× | $2.00 | 40.3 | 71.8 | 49.6 | $0.050 | 36 |
| inclusionai/ling-3.0-flash-sante | 46.7B | 0.26% | 2.62× | — | — | — | — | — | — |
| openai/gpt-5.6-luna-pro | 46.5B | 0.26% | 0.71× | — | — | — | — | — | — |
| mistralai/mistral-nemo | 40.8B | 0.23% | 1.39× | — | — | — | — | — | — |
| anthropic/claude-fable-5 | 40.7B | 0.22% | 1.31× | $10.00 | 49.7 | 76.5 | 51.0 | $0.201 | 46 |
| google/gemma-4-26b-a4b-it | 40.7B | 0.22% | 0.75× | — | — | — | — | — | — |
| anthropic/claude-haiku-4.5 | 38.5B | 0.21% | 1.00× | $1.00 | 17.6 | 43.9 | 10.3 | $0.057 | 70 |
| xiaomi/mimo-v2.5-pro | 37.0B | 0.20% | 0.62× | $0.304 | 26.4 | 60.2 | 22.7 | $0.011 | 17 |
| deepseek/deepseek-v4-flash-vision-exp | 36.1B | 0.20% | 0.79× | — | — | — | — | — | — |
| qwen/qwen3.8-27b | 33.9B | 0.19% | 1.06× | $0.150 | 33.9 | 68.1 | 46.5 | $0.004 | 4 |
| google/gemini-3.5-flash-lite | 32.7B | 0.18% | 1.20× | $0.150 | 22.7 | 49.3 | 15.9 | $0.007 | 92 |
| openai/gpt-4o-mini | 32.4B | 0.18% | 0.89× | — | — | — | — | — | — |
| openai/gpt-oss-20b | 32.2B | 0.18% | 0.68× | — | — | — | — | — | — |
| meta/muse-spark-1.3 | 30.7B | 0.17% | 1.59× | — | — | — | — | — | — |
| google/gemini-3.1-pro-preview | 29.7B | 0.16% | 0.83× | $1.00 | 30.4 | 68.8 | 10.3 | $0.033 | 88 |
| moonshotai/kimi-k2.6 | 27.8B | 0.15% | 0.99× | — | — | — | — | — | — |
| openai/gpt-5.4-mini | 23.5B | 0.13% | 1.39× | $0.375 | 24.6 | 56.1 | 19.7 | $0.015 | 31 |
| nex-agi/nex-n2.5-mini | 22.4B | 0.12% | 4.53× | — | — | — | — | — | — |
| openai/gpt-5-mini | 21.2B | 0.12% | 0.87× | $0.125 | 17.4 | 15.6 | 8.9 | $0.007 | 54 |
| google/gemini-3.5-flash | 20.9B | 0.12% | 1.07× | $0.750 | 33.0 | 70.1 | 27.3 | $0.023 | 123 |
| qwen/qwen3.7-plus | 19.8B | 0.11% | 1.51× | $0.320 | 25.8 | 55.9 | 19.7 | $0.012 | 10 |
| openai/text-embedding-3-small | 19.5B | 0.11% | 0.86× | — | — | — | — | — | — |
| openai/gpt-5.4-nano | 18.2B | 0.10% | 0.87× | $0.100 | 21.2 | 56.1 | 17.7 | $0.005 | 41 |
| anthropic/claude-opus-4.6 | 18.2B | 0.10% | 0.78× | — | — | — | — | — | — |
| qwen/qwen3-embedding-8b | 17.8B | 0.10% | 0.95× | — | — | — | — | — | — |
| cohere/north-mini-code | 17.2B | 0.09% | 0.73× | — | — | — | — | — | — |
| google/gemini-3.6-flash | 16.9B | 0.09% | 0.19× | $0.375 | 34.3 | 69.2 | 30.2 | $0.011 | 56 |
| thinkingmachines/inkling-small | 16.7B | 0.09% | 1.23× | $0.450 | 26.1 | 52.9 | 25.0 | $0.017 | 103 |
| inclusionai/ling-3.0-flash | 16.5B | 0.09% | 1.10× | — | — | — | — | — | — |
| google/gemini-3.1-flash-lite-preview | 16.1B | 0.09% | 1.01× | $0.125 | 16.0 | 34.7 | 3.2 | $0.008 | 58 |
| meta-llama/llama-3.1-8b-instruct | 15.4B | 0.09% | 1.21× | — | — | — | — | — | — |
| openai/gpt-4.1-nano | 14.8B | 0.08% | 1.48× | — | — | — | — | — | — |
| openai/gpt-4.1-mini | 12.9B | 0.07% | 1.01× | — | — | — | — | — | — |
| qwen/qwen3-235b-a22b-2507 | 12.7B | 0.07% | 1.15× | — | — | — | — | — | — |
| poolside/laguna-xs-2.1 | 12.4B | 0.07% | 0.66× | — | — | — | — | — | — |
| anthropic/claude-sonnet-4.5 | 11.7B | 0.06% | 0.84× | $3.00 | 21.2 | 52.1 | 17.5 | $0.141 | 2 |
| x-ai/grok-4.5 | 11.2B | 0.06% | 0.59× | $2.00 | 39.1 | 72.4 | 42.1 | $0.051 | 54 |
| openai/gpt-5.4 | 11.2B | 0.06% | 0.63× | — | — | — | — | — | — |
| qwen/qwen3.5-flash-02-23 | 10.3B | 0.06% | 1.00× | — | — | — | — | — | — |
| openai/gpt-5.5 | 9.8B | 0.05% | 0.33× | $2.50 | 38.6 | 74.9 | 37.3 | $0.065 | 37 |
| voyageai/rerank-2.5-lite | 9.8B | 0.05% | 2.26× | — | — | — | — | — | — |
| moonshotai/kimi-k2.7-code | 9.7B | 0.05% | 0.98× | $0.680 | 26.3 | 60.8 | 22.5 | $0.026 | 19 |
| moonshotai/kimi-k2.5 | 9.7B | 0.05% | 0.83× | — | — | — | — | — | — |
| minimax/minimax-m2.7 | 9.5B | 0.05% | 0.17× | $0.210 | 23.2 | 52.6 | 16.8 | $0.009 | 31 |
| anthropic/claude-opus-4.7 | 9.1B | 0.05% | 0.31× | — | — | — | — | — | — |
| qwen/qwen3.6-35b-a3b | 8.9B | 0.05% | 0.73× | $0.050 | 18.8 | 41.9 | 15.0 | $0.003 | 46 |
| openai/gpt-6-astra-pro | 8.8B | 0.05% | 1.37× | — | — | — | — | — | — |
| openai/gpt-5.6-sol-pro | 8.4B | 0.05% | 0.54× | — | — | — | — | — | — |
| z-ai/glm-5.1 | 8.3B | 0.05% | 0.82× | $0.966 | 26.4 | 55.8 | 25.2 | $0.037 | 25 |
| openai/gpt-5-nano | 8.3B | 0.05% | 0.50× | — | — | — | — | — | — |
| meta-llama/llama-4-scout | 8.1B | 0.04% | 2.13× | — | — | — | — | — | — |
| x-ai/grok-4.3 | 8.0B | 0.04% | 0.78× | $1.25 | 25.4 | 42.2 | 17.2 | $0.049 | 80 |
| google/gemini-2.5-pro | 7.9B | 0.04% | 0.93× | $0.625 | 16.7 | 33.3 | 3.5 | $0.037 | 81 |
| openai/gpt-4.1 | 7.6B | 0.04% | 0.88× | — | — | — | — | — | — |
| google/gemma-3-27b-it | 7.2B | 0.04% | 0.92× | — | — | — | — | — | — |
| deepseek/deepseek-chat-v3.1 | 7.2B | 0.04% | 1.05× | — | — | — | — | — | — |
| openai/text-embedding-3-large | 7.0B | 0.04% | 0.55× | — | — | — | — | — | — |
| z-ai/glm-5 | 6.8B | 0.04% | 1.06× | — | — | — | — | — | — |
| qwen/qwen3.5-9b | 6.5B | 0.04% | 1.20× | — | — | — | — | — | — |
| z-ai/glm-4.7 | 6.3B | 0.03% | 0.85× | — | — | — | — | — | — |
| google/gemini-embedding-2 | 6.1B | 0.03% | 1.13× | — | — | — | — | — | — |
| openai/gpt-5.2 | 6.1B | 0.03% | 1.18× | — | — | — | — | — | — |
| openai/gpt-5.3-codex | 5.7B | 0.03% | 1.13× | — | — | — | — | — | — |
| x-ai/grok-4.20 | 5.4B | 0.03% | 1.06× | — | — | — | — | — | — |
| deepseek/deepseek-chat-v3-0324 | 5.2B | 0.03% | 1.11× | — | — | — | — | — | — |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning | 4.6B | 0.03% | 0.81× | — | — | — | — | — | — |
| meta-llama/llama-3.3-70b-instruct | 4.5B | 0.03% | 0.73× | — | — | — | — | — | — |
| qwen/qwen3-30b-a3b-instruct-2507 | 4.3B | 0.02% | 0.68× | — | — | — | — | — | — |
| minimax/minimax-m2.5 | 4.1B | 0.02% | 0.64× | — | — | — | — | — | — |
| qwen/qwen3-coder-next | 4.1B | 0.02% | 1.03× | $0.120 | 10.1 | 36.2 | 3.6 | $0.012 | 63 |
| qwen/qwen3.5-397b-a17b | 3.8B | 0.02% | 0.66× | $0.390 | 19.1 | 48.2 | 10.6 | $0.020 | 76 |
| mistralai/mistral-small-2603 | 3.7B | 0.02% | — | $0.150 | 11.5 | 26.6 | 1.4 | $0.013 | 56 |
| perplexity/pplx-embed-v1-0.6b | 3.1B | 0.02% | 0.48× | — | — | — | — | — | — |
| qwen/qwen3.8-2.4t-a95b | 3.1B | 0.02% | 0.48× | $2.00 | 40.0 | 71.9 | 50.4 | $0.050 | 30 |
| qwen/qwen3.5-35b-a3b | 3.0B | 0.02% | 0.67× | — | — | — | — | — | — |
| qwen/qwen3-32b | 2.8B | 0.02% | 0.59× | — | — | — | — | — | — |
| baai/bge-m3 | 2.7B | 0.02% | 0.69× | — | — | — | — | — | — |
| amazon/nova-micro-v1 | 2.7B | 0.01% | 0.46× | — | — | — | — | — | — |
| meta/muse-spark-1.2-contributor | 2.6B | 0.01% | 0.12× | — | — | — | — | — | — |
| qwen/qwen3.5-122b-a10b | 2.5B | 0.01% | — | $0.260 | 16.2 | 45.7 | 9.6 | $0.016 | 57 |
| stepfun/step-3.7-flash | 2.3B | 0.01% | 0.04× | — | — | — | — | — | — |
| qwen/qwen3.7-max | 2.2B | 0.01% | 0.41× | $1.48 | 29.9 | 66.0 | 23.9 | $0.049 | 63 |
| meta/muse-spark-1.2 | 1.6B | 0.01% | — | $1.25 | 39.8 | 72.2 | 44.0 | $0.031 | 110 |
| qwen/qwen3.6-27b | 1.6B | 0.01% | — | $0.300 | 21.9 | 53.7 | 20.1 | $0.014 | 8 |
| deepseek/deepseek-v3.1-terminus | 1.1B | 0.01% | — | $0.270 | 15.4 | 43.5 | 8.9 | $0.018 | 18 |
| meituan/longcat-2.0 | 801M | <0.01% | — | $0.300 | 19.7 | 45.3 | 15.9 | $0.015 | 33 |
| mistralai/mistral-medium-3-5 | 723M | <0.01% | — | $1.50 | 14.9 | 46.9 | 9.4 | $0.101 | 62 |
| tencent/hy3-preview | 676M | <0.01% | — | $0.180 | 25.8 | 58.8 | 25.6 | $0.007 | 74 |
| meta/muse-spark-1.1 | 536M | <0.01% | — | $1.25 | 34.3 | 71.3 | 27.5 | $0.036 | 197 |
| arcee-ai/trinity-large-thinking | 483M | <0.01% | — | $0.250 | 10.9 | 25.8 | 1.2 | $0.023 | 78 |
| ibm-granite/granite-4.2-8b | 460M | <0.01% | — | $0.060 | 11.8 | 22.4 | 3.7 | $0.005 | 129 |
| deepseek/deepseek-r1 | 356M | <0.01% | — | $0.700 | 11.4 | 24.6 | 1.1 | $0.061 | 20 |
| qwen/qwen3-235b-a22b-thinking-2507 | 285M | <0.01% | — | $0.230 | 12.7 | 22.1 | 1.3 | $0.018 | 60 |
| inception/mercury-2 | 246M | <0.01% | — | $0.250 | 11.5 | 31.1 | 4.0 | $0.022 | 160 |
| cohere/command-a | 6M | <0.01% | — | $2.50 | 13.9 | 27.8 | 3.6 | $0.180 | 45 |
| openai/o3-mini-high | 1M | <0.01% | — | $1.10 | 11.0 | 16.3 | 0.9 | $0.100 | 47 |
| google/gemma-4-31b-it:freefree | — | — | — | — | 15.4 | — | — | — | — |
| inclusionai/ling-3.0-flash-vl:freefree | — | — | — | — | 24.8 | — | — | — | — |
| nvidia/nemotron-3-super-120b-a12b:freefreetrains on input | — | — | — | — | 13.6 | — | — | — | — |
| nvidia/nemotron-3-ultra-550b-a55b:freefreetrains on input | — | — | — | — | 23.4 | — | — | — | — |
| nvidia/nemotron-3.5-lightning:freefreetrains on input | — | — | — | — | 13.6 | — | — | — | — |
| thinkingmachines/inkling-small:freefreetrains on input | — | — | — | — | 26.1 | — | — | — | — |
| thinkingmachines/inkling:freefreetrains on input | — | — | — | — | 25.5 | — | — | — | — |
Source: OpenRouter’s public catalog and rankings, read once a day by a collector this instrument runs on its own hardware. The gateway publishes no history — every number here exists because it was recorded on the day it was true, and a missed day cannot be bought back at any price. Figures describe traffic routed through this one gateway; traffic sent directly to a vendor never appears in it.